Supervisor: Ayaz Samadli Key words: Open CV, Machine Learning, Deep Learning, Raspberry Pi, Arduino Uno,
L298H-bridge, Lane Detection, Object Detection, Traffic Light Recognition.
Abstract The main objective of the proposed system is to build self-driving car
prototype that uses the Raspberry Pi as its central processing unit with
peripheral devices such as Arduino Uno, raspiCam2, L298H bridge.[2021]
Software and algorithmic innovations are also essential for many of the
technolgical advancements that enable self-driving automobiles, especially
machine learning and deep learning techniques, image processing
alogorithms,path planning make the system move automatically without any
human intervention to the destination. In our project we have used Python
programming for Computer Vision and Deep Learning and C++ in Arduino Uno.
Introduction It is undeniable fact that autonomous vehicles will be centerpiece of our
future world.As the number of accidents increases because of a rise in the
number of vehicles on the road and driver carelessness autonomous
vehicles provide us safe transportation and high chance to prevent accidents
due to its highly developed techonology.Moreover we can say that
automated vehicles will play a crucial role in order to decrease obstraction of
traffic and will be able to provide mobility for whose are disabled to drive non-
autonomous vehicles.[2019]
Our project is to build self-driving car with moving along the
lane,detecting and following different traffic lights. Firstly, we get continuous
images taken over raspiCam2 and output obtained from ML and CV
algorithms send to the H bridge which is for controling the left and right
motors through Arduino Uno.[2021]
Design Architecture and Hardwares used In our autonomous car we have 4 DC motor for wheels separately.The
main processor used for this project is Raspberry Pi 3 B+. Raspberry Pi 3 B+
is a 64-bit quad core processor running at 1.4GHz.Raspian Operating system
is downloaded in it to.Also,it includes wifi module which is used to connect